Addressing PR comments by Copilot · Pull Request #7 · raux/BonsAIDE

Copilot · 2026-02-23T04:09:15Z

🔒 GitHub Advanced Security automatically protects Copilot coding agent pull requests. You can protect all pull requests by enabling Advanced Security for your repositories. Learn more about Advanced Security.

Co-authored-by: raux <5723643+raux@users.noreply.github.com>

raux · 2026-02-23T04:15:15Z

@codex[agent]

…lity Co-authored-by: raux <5723643+raux@users.noreply.github.com>

Copilot

Pull request overview

This pull request adds a "Test Connection" feature to the BonsAIDE application, allowing users to verify connectivity to their LM Studio server before performing operations. The feature is implemented for both the VSCode extension and standalone web server modes.

Changes:

Adds test connection button and status display to the UI (webview and client interfaces)
Implements backend logic to validate URL format and send a minimal test request to LM Studio
Provides visual feedback (success/error/testing states) via color-coded status messages

Reviewed changes

Copilot reviewed 6 out of 6 changed files in this pull request and generated 6 comments.

Show a summary per file

File	Description
src/server.ts	Adds `testConnection` command handler for standalone server mode with URL validation and LLM test request
src/extension.ts	Adds `testConnection` command handler for VSCode extension mode with URL validation and LLM test request
media/webview.html	Adds test connection button, status span, and styling for the VSCode extension webview UI
client/index.html	Adds test connection button and status span for the standalone web client UI
client/js/app.js	Implements click handler for test connection button and result message handling
client/css/styles.css	Adds CSS styling for connection test status states (testing, success, error)

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

Copilot · 2026-02-23T04:28:47Z

-    <div style="margin:6px 0; display:flex; flex-wrap:wrap; gap:8px;">
+    <div style="margin:6px 0; display:flex; flex-wrap:wrap; gap:8px; align-items:center;">
        <label>LM_Studio URL:
            <input id="baseUrlInput" type="text" size="40" placeholder="http://localhost:1234/v1" />


The placeholder value includes the protocol prefix "http://localhost:1234/v1", but the URL validation regex at line 563 in extension.ts expects URLs without the protocol (host:port/path pattern). This will cause the validation to fail if a user copies the placeholder value. The placeholder should be changed to "localhost:1234/v1" to match the expected format.

Suggested change

<input id="baseUrlInput" type="text" size="40" placeholder="http://localhost:1234/v1" />

<input id="baseUrlInput" type="text" size="40" placeholder="localhost:1234/v1" />

Copilot · 2026-02-23T04:28:47Z

+            // Validate URL format (should be host:port/path pattern)
+            if (!/^[\w.-]+(:\d+)?(\/[\w./]*)?$/.test(testUrl)) {
+              throw new Error('Invalid URL format. Expected format: host:port/path (e.g., localhost:1234/v1)');
+            }
+
+            const res = await fetch(`http://${testUrl}/chat/completions`, {


The URL validation regex rejects URLs that contain the protocol prefix. However, looking at extension.ts line 899, there's code that uses a default URL with the "http://" protocol prefix ("http://10.184.201.141:1234/v1"). The regex should either be updated to optionally accept the protocol prefix, or all code should be consistent about expecting URLs without the protocol. Consider updating the regex to: /^(https?://)?[\w.-]+(:\d+)?(/[\w./]*)?$/ and strip the protocol before prepending "http://" in the fetch call.

Suggested change

// Validate URL format (should be host:port/path pattern)

if (!/^[\w.-]+(:\d+)?(\/[\w./]*)?$/.test(testUrl)) {

throw new Error('Invalid URL format. Expected format: host:port/path (e.g., localhost:1234/v1)');

}

const res = await fetch(`http://${testUrl}/chat/completions`, {

// Validate URL format (allows optional http/https protocol and host:port/path pattern)

if (!/^(https?:\/\/)?[\w.-]+(:\d+)?(\/[\w./]*)?$/.test(testUrl)) {

throw new Error('Invalid URL format. Expected format: host:port/path (e.g., localhost:1234/v1) or with protocol (e.g., http://localhost:1234/v1)');

}

const normalizedUrl = testUrl.replace(/^https?:\/\//, '');

const res = await fetch(`http://${normalizedUrl}/chat/completions`, {

Copilot · 2026-02-23T04:28:48Z

+      // Validate URL format (should be host:port/path pattern)
+      if (!/^[\w.-]+(:\d+)?(\/[\w./]*)?$/.test(testUrl)) {
+        throw new Error('Invalid URL format. Expected format: host:port/path (e.g., localhost:1234/v1)');
+      }
+
+      const res = await fetch(`http://${testUrl}/chat/completions`, {


The URL validation regex rejects URLs that contain the protocol prefix. However, the media/webview.html placeholder shows "http://localhost:1234/v1" (with protocol). The regex should either be updated to optionally accept the protocol prefix, or all code should be consistent about expecting URLs without the protocol. Consider updating the regex to: /^(https?://)?[\w.-]+(:\d+)?(/[\w./]*)?$/ and strip the protocol before prepending "http://" in the fetch call.

Suggested change

// Validate URL format (should be host:port/path pattern)

if (!/^[\w.-]+(:\d+)?(\/[\w./]*)?$/.test(testUrl)) {

throw new Error('Invalid URL format. Expected format: host:port/path (e.g., localhost:1234/v1)');

}

const res = await fetch(`http://${testUrl}/chat/completions`, {

// Normalize and validate URL format (accept optional protocol, ensure host:port/path pattern)

const normalizedTestUrl = testUrl.replace(/^https?:\/\//, '');

if (!/^(https?:\/\/)?[\w.-]+(:\d+)?(\/[\w./]*)?$/.test(testUrl)) {

throw new Error('Invalid URL format. Expected format similar to: localhost:1234/v1 or http://localhost:1234/v1');

}

const res = await fetch(`http://${normalizedTestUrl}/chat/completions`, {

Copilot · 2026-02-23T04:28:48Z

+            const res = await fetch(`http://${testUrl}/chat/completions`, {
+              method: 'POST',
+              headers: {
+                'Content-Type': 'application/json',
+                'Authorization': 'Bearer lm-studio',
+              },
+              body: JSON.stringify({
+                model: testModel,
+                messages: [{ role: 'user', content: 'Say "connected" in one word.' }],
+                temperature: 0,
+                max_tokens: 10,
+                stream: false,
+              }),
+            });
+


The connection test fetch request has no timeout configured. If the LM Studio server is unreachable or not responding, the user may have to wait for the default fetch timeout (which can be very long). Consider adding an AbortController with a reasonable timeout (e.g., 10 seconds) to provide better user experience.

Suggested change

const res = await fetch(`http://${testUrl}/chat/completions`, {

method: 'POST',

headers: {

'Content-Type': 'application/json',

'Authorization': 'Bearer lm-studio',

},

body: JSON.stringify({

model: testModel,

messages: [{ role: 'user', content: 'Say "connected" in one word.' }],

temperature: 0,

max_tokens: 10,

stream: false,

}),

});

const controller = new AbortController();

const timeoutMs = 10_000;

const timeoutId = setTimeout(() => controller.abort(), timeoutMs);

const res = await (async () => {

try {

return await fetch(`http://${testUrl}/chat/completions`, {

method: 'POST',

headers: {

'Content-Type': 'application/json',

'Authorization': 'Bearer lm-studio',

},

body: JSON.stringify({

model: testModel,

messages: [{ role: 'user', content: 'Say "connected" in one word.' }],

temperature: 0,

max_tokens: 10,

stream: false,

}),

signal: controller.signal,

});

} finally {

clearTimeout(timeoutId);

}

})();

Copilot · 2026-02-23T04:28:48Z

+      const res = await fetch(`http://${testUrl}/chat/completions`, {
+        method: 'POST',
+        headers: {
+          'Content-Type': 'application/json',
+          'Authorization': 'Bearer lm-studio',
+        },
+        body: JSON.stringify({
+          model: testModel,
+          messages: [{ role: 'user', content: 'Say "connected" in one word.' }],
+          temperature: 0,
+          max_tokens: 10,
+          stream: false,
+        }),
+      });


The connection test fetch request has no timeout configured. If the LM Studio server is unreachable or not responding, the user may have to wait for the default fetch timeout (which can be very long). Consider adding an AbortController with a reasonable timeout (e.g., 10 seconds) to provide better user experience.

Copilot · 2026-02-23T04:28:48Z

+        if (message.command === 'testConnection') {
+          const testUrl = message.baseUrl || baseUrl;
+          const testModel = message.model || LLMmodel;
+          bonsaiLog('Testing connection to:', testUrl, 'with model:', testModel);
+          panel.webview.postMessage({ command: 'loading', text: 'Testing connection...' });
+
+          try {
+            // Validate URL format (should be host:port/path pattern)
+            if (!/^[\w.-]+(:\d+)?(\/[\w./]*)?$/.test(testUrl)) {
+              throw new Error('Invalid URL format. Expected format: host:port/path (e.g., localhost:1234/v1)');
+            }
+
+            const res = await fetch(`http://${testUrl}/chat/completions`, {
+              method: 'POST',
+              headers: {
+                'Content-Type': 'application/json',
+                'Authorization': 'Bearer lm-studio',
+              },
+              body: JSON.stringify({
+                model: testModel,
+                messages: [{ role: 'user', content: 'Say "connected" in one word.' }],
+                temperature: 0,
+                max_tokens: 10,
+                stream: false,
+              }),
+            });
+
+            if (!res.ok) {
+              const text = await res.text().catch(() => '');
+              throw new Error(`HTTP ${res.status} ${res.statusText}${text ? ` - ${text}` : ''}`);
+            }
+
+            const json: any = await res.json();
+            const output = json?.choices?.[0]?.message?.content?.trim?.() ?? '';
+            bonsaiLog('Connection test successful. Response:', output);
+            panel.webview.postMessage({ command: 'connectionTestResult', success: true, message: `✓ Connected! Model responded: "${output}"` });
+          } catch (err: any) {
+            bonsaiLog('Connection test failed:', err?.message || err);
+            panel.webview.postMessage({ command: 'connectionTestResult', success: false, message: `✗ Connection failed: ${err?.message || err}` });
+          }
+          return;
+        }


The testConnection handler code in extension.ts (lines 555-596) is nearly identical to the code in server.ts (lines 493-534). This duplication makes maintenance harder and increases the risk of bugs when changes are made to one but not the other. Consider extracting this logic into a shared utility function that both files can use, or at minimum document this duplication so future maintainers are aware they need to update both places.

Initial plan

7abe9a0

Copilot AI assigned Copilot and raux Feb 23, 2026

Copilot started work on behalf of raux February 23, 2026 04:09 View session

Add Test Connection button to verify LM Studio URL connectivity

25fa112

Co-authored-by: raux <5723643+raux@users.noreply.github.com>

Address code review: add URL validation and aria-labels for accessibi…

0683c29

…lity Co-authored-by: raux <5723643+raux@users.noreply.github.com>

Copilot AI changed the title ~~[WIP] Add button to test LM Studio URL connection and model response~~ Add Test Connection button for LM Studio URL verification Feb 23, 2026

Copilot AI requested a review from raux February 23, 2026 04:17

Copilot finished work on behalf of raux February 23, 2026 04:17

Codex started work on behalf of raux February 23, 2026 04:18 View session

Codex AI changed the title ~~Add Test Connection button for LM Studio URL verification~~ Addressing PR comments Feb 23, 2026

Codex finished work on behalf of raux February 23, 2026 04:19

raux marked this pull request as ready for review February 23, 2026 04:24

Copilot AI review requested due to automatic review settings February 23, 2026 04:24

raux merged commit 3c35713 into main Feb 23, 2026
1 check passed

Copilot started reviewing on behalf of raux February 23, 2026 04:25 View session

Copilot AI reviewed Feb 23, 2026

View reviewed changes

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Addressing PR comments#7

Addressing PR comments#7
raux merged 3 commits into
mainfrom
copilot/add-url-connection-test-button

Copilot AI commented Feb 23, 2026 •

edited by Codex AI

Loading

Uh oh!

raux commented Feb 23, 2026

Uh oh!

Uh oh!

Copilot AI left a comment

Uh oh!

Copilot AI Feb 23, 2026

Uh oh!

Copilot AI Feb 23, 2026

Uh oh!

Copilot AI Feb 23, 2026

Uh oh!

Copilot AI Feb 23, 2026

Uh oh!

Copilot AI Feb 23, 2026

Uh oh!

Copilot AI Feb 23, 2026

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

3 participants

	<input id="baseUrlInput" type="text" size="40" placeholder="http://localhost:1234/v1" />
	<input id="baseUrlInput" type="text" size="40" placeholder="localhost:1234/v1" />

-            // Validate URL format (should be host:port/path pattern)
-            if (!/^[\w.-]+(:\d+)?(\/[\w./]*)?$/.test(testUrl)) {
-              throw new Error('Invalid URL format. Expected format: host:port/path (e.g., localhost:1234/v1)');
-            }
-            const res = await fetch(`http://${testUrl}/chat/completions`, {
+            // Validate URL format (allows optional http/https protocol and host:port/path pattern)
+            if (!/^(https?:\/\/)?[\w.-]+(:\d+)?(\/[\w./]*)?$/.test(testUrl)) {
+              throw new Error('Invalid URL format. Expected format: host:port/path (e.g., localhost:1234/v1) or with protocol (e.g., http://localhost:1234/v1)');
+            }
+            const normalizedUrl = testUrl.replace(/^https?:\/\//, '');
+            const res = await fetch(`http://${normalizedUrl}/chat/completions`, {

Conversation

Copilot AI commented Feb 23, 2026 • edited by Codex AI Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

raux commented Feb 23, 2026

Uh oh!

Uh oh!

Copilot AI left a comment

Choose a reason for hiding this comment

Pull request overview

Reviewed changes

Uh oh!

Copilot AI Feb 23, 2026

Choose a reason for hiding this comment

Uh oh!

Copilot AI Feb 23, 2026

Choose a reason for hiding this comment

Uh oh!

Copilot AI Feb 23, 2026

Choose a reason for hiding this comment

Uh oh!

Copilot AI Feb 23, 2026

Choose a reason for hiding this comment

Uh oh!

Copilot AI Feb 23, 2026

Choose a reason for hiding this comment

Uh oh!

Copilot AI Feb 23, 2026

Choose a reason for hiding this comment

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

3 participants

Copilot AI commented Feb 23, 2026 •

edited by Codex AI

Loading